Home
Resource
Railroad trespassing detection and analysis using video analytics
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(1.97 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Zaman, Asim F.. Railroad trespassing detection and analysis using video analytics. Retrieved from https://doi.org/doi:10.7282/t3-mc8m-nv44

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleRailroad trespassing detection and analysis using video analytics
NameZaman, Asim F. (author); Liu, Xiang (chair); Gong, Jie (internal member); Jin, Jing (internal member); Rutgers University; School of Graduate Studies
Date Created2018
Other Date2018-10 (degree)
SubjectCivil and Environmental Engineering, Railroads--Safety measures, Data logging
Extent1 online resource (76 pages : illustrations)
DescriptionTrespassing is the leading cause of rail-related deaths and has been on the rise for the past ten years. Detection of trespassing of railroad tracks is critical to understand and prevent trespassing fatalities. The volume of video data in the railroad industry has increased significantly in recent years. Surveillance cameras are situated on nearly every part of the railroad system such as inside the cab, along the track, at grade crossings, and in stations. These camera systems are manually monitored; either live or subsequently reviewed in an archive, which requires an immense amount of labor. To make the video analysis much less labor-intensive, this thesis develops two frameworks for utilizing Artificial Intelligence (AI) technologies for the extraction of useful information from these big video datasets.
The first framework has been implemented on video data from one grade crossing in New Jersey. The AI algorithm can automatically detect unsafe trespassing of railroad tracks. To date, the AI algorithm has analyzed hours of video data and correctly detected all trespassing events. The algorithm was presented to industry professionals and useful feedback was gathered suggesting several improvements to meet the needs of the railroad industry. This feedback led to the development of the second framework with new capabilities, and an expanded scope of video data reviewed.
The second framework was implemented on three railroad video live streams, a grade crossing and two non-grade crossings, in the United States. This AI algorithm automatically detects trespassing events, differentiates between the type of violator (car, motorcycle, truck, pedestrian etc.) and sends an alert text message to a designated destination with important information including a video clip of the trespassing event. In this study, the AI has analyzed hours of live footage with no false positives or missed detections.
This thesis indicates the promise of using AI for automated analysis of railroad big video data, thereby supporting data-driven railroad safety research. This thesis, and its sequent studies, aim to provide the railroad industry with next-generation big data analysis methods and tools for quickly and reliably processing large volumes of video data to better understand human factors in railroad safety research.
NoteM.S.
NoteIncludes bibliographical references
Noteby Asim F. Zaman
Genretheses, ETD graduate
Persistent URLhttps://doi.org/doi:10.7282/t3-mc8m-nv44
Languageeng
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024